Assignment in intro to neural computation

Part C&D

By : Michael trushkin

Data

All data Is two dimensional , <x,y> where -1 <= x, y <= 1.
The data is all data points <x, y> where x is of the form m/100 where m is an integer between -100 and +100
and y is of the form n/100 with n an integer between -100 and +100.

suppose that:

<x,y> has value of 1 iff :

1/2 < x^2+y^2 < 3/4

About Part C

Try to traing a Neural network using back propogation, to predict the given function.
show the output of each of the neuron's in the network.

what we will do

  • we will build out own neural network class, and implement back prop.

About the neural network

  • we will use mini-batch training, our model supports batches of any sizes.
  • we use momentum model meaning the Gradient at time t, is combined with fraction of the gradient of time t-1
  • the momentum level is set to 0.5 by default and the learning rate is 0.1 by default.

we use momentum because from some test's i have made it simply converges faster.